中文标题#
HyperDiff：超圖引導的擴散模型用於 3D 人體姿態估計
英文标题#
HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation
中文摘要#
單目 3D 人體姿態估計（HPE）在從 2D 到 3D 的提升過程中常常遇到深度模糊和遮擋等挑戰。此外，傳統方法在利用骨骼結構信息時可能忽略多尺度骨骼特徵，這可能會對姿態估計的準確性產生負面影響。為了解決這些挑戰，本文引入了一種新穎的 3D 姿態估計方法，HyperDiff，該方法將擴散模型與 HyperGCN 相結合。擴散模型有效地捕捉數據不確定性，緩解深度模糊和遮擋。同時，作為去噪器的 HyperGCN 採用多粒度結構，準確建模關節之間的高階相關性。這提高了模型的去噪能力，特別是在複雜姿態的情況下。實驗結果表明，HyperDiff 在 Human3.6M 和 MPI-INF-3DHP 數據集上達到了最先進的性能，並能靈活適應不同的計算資源，以平衡性能和效率。
英文摘要#
Monocular 3D human pose estimation (HPE) often encounters challenges such as depth ambiguity and occlusion during the 2D-to-3D lifting process. Additionally, traditional methods may overlook multi-scale skeleton features when utilizing skeleton structure information, which can negatively impact the accuracy of pose estimation. To address these challenges, this paper introduces a novel 3D pose estimation method, HyperDiff, which integrates diffusion models with HyperGCN. The diffusion model effectively captures data uncertainty, alleviating depth ambiguity and occlusion. Meanwhile, HyperGCN, serving as a denoiser, employs multi-granularity structures to accurately model high-order correlations between joints. This improves the model's denoising capability especially for complex poses. Experimental results demonstrate that HyperDiff achieves state-of-the-art performance on the Human3.6M and MPI-INF-3DHP datasets and can flexibly adapt to varying computational resources to balance performance and efficiency.
文章页面#
HyperDiff：超圖引導的擴散模型用於 3D 人體姿態估計
PDF 獲取#
抖音掃碼查看更多精彩內容